Triple
T28990445
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shanghai Public Transportation Card |
E736010
|
entity |
| Predicate | allowsTopUpAt |
P27918
|
FINISHED |
| Object | metro stations |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: metro stations | Statement: [Shanghai Public Transportation Card, allowsTopUpAt, metro stations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: allowsTopUpAt Context triple: [Shanghai Public Transportation Card, allowsTopUpAt, metro stations]
-
A.
topUpMethod
Indicates the method or mechanism used to add funds or value to an account, balance, or service.
-
B.
canPay
Indicates that one entity has the ability or authorization to make a payment to another entity or to settle a specified obligation.
-
C.
topUpLocations
chosen
Indicates locations where a balance, credit, or value can be increased or recharged for a related account, service, or device.
-
D.
hasOpalCardTopUp
Indicates that an entity has performed or received a monetary top-up on an Opal card.
-
E.
canCharge
Indicates that one entity has the ability or permission to charge another entity, typically in the sense of applying a cost, fee, or electrical charge.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f077eacd0481908ef0bafd74491cd0 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f72921cf2c8190909bb53f78bcc890 |
completed | May 3, 2026, 10:53 a.m. |
| PD | Predicate disambiguation | batch_69f7283d8cec8190b524c144948bc4ec |
completed | May 3, 2026, 10:49 a.m. |
Created at: April 28, 2026, 9:24 a.m.